© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8891
    Prev
    Next
    INDEX
    Explanations

    contextual phrases related to the consequences of emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.80
    how
    -0.53
    all
    -0.51
    some
    -0.50
     SIMBAD
    -0.49
     ἔ
    -0.49
    Nation
    -0.48
     NATION
    -0.48
    GeoNames
    -0.48
     lop
    -0.47
    POSITIVE LOGITS
     Мексичка
    0.88
     تانيه
    0.86
     GoogleFonts
    0.78
    BufferException
    0.78
     TextInputType
    0.76
    Rüyada
    0.76
    FailureListener
    0.75
     оригіналу
    0.74
    TProtocol
    0.74
    StatusBadRequest
    0.73
    Activations Density 2.068%

    No Known Activations